tree-graph-rag
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent PostgreSQL RAG database guide with expected example scripts for storing and retrieving document tree and graph data.
Before installing or adapting this skill, confirm that your documents may be stored in PostgreSQL and passed to your selected LLM extractor, preserve workspace/user authorization filters, and test the ingestion code on a staging database before using it in production.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
67/67 vendors flagged this skill as clean.